发现 Skills

Use when building iOS/macOS applications with Swift 5.9+, SwiftUI, or async/await concurrency. Invoke for protocol-oriented programming, SwiftUI state management, actors, and server-side Swift.

Multi-agent code review pipeline. Stage 1: Explorer scans git diff and maps impact scope. Stage 2: Reviewer checks every changed file against coding standards, security rules, and anti-patterns from CLAUDE.md. Outputs a structured 4-level report (CRITICAL/HIGH/MEDIUM/LOW). Use after making changes, before committing, or when reviewing a PR.

Set up a local Kubernetes development loop with CAST AI cost monitoring. Use when building cost-aware deployments, testing autoscaler policies, or iterating on Terraform CAST AI configurations locally. Trigger with phrases like "cast ai dev setup", "cast ai local testing", "develop with cast ai", "cast ai terraform dev".

Execute a self-learning system that captures corrections during sessions and syncs them to CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something. Trigger with phrases like "remember this", "don't forget", "use X not Y", or "actually...".

Optimize CodeRabbit costs through seat management, repo selection, and review scope tuning. Use when analyzing CodeRabbit billing, reducing per-seat costs, or implementing usage monitoring and budget optimization. Trigger with phrases like "coderabbit cost", "coderabbit billing", "reduce coderabbit costs", "coderabbit pricing", "coderabbit expensive", "coderabbit budget".

Understand and handle CodeRabbit and GitHub API rate limits for review automation. Use when hitting rate limits on @coderabbitai commands, automating review queries, or building scripts that interact with CodeRabbit via the GitHub API. Trigger with phrases like "coderabbit rate limit", "coderabbit throttling", "coderabbit too many requests", "github api rate limit coderabbit".

Configure Databricks job notifications, webhooks, and event handling. Use when setting up Slack/Teams notifications, configuring alerts, or integrating Databricks events with external systems. Trigger with phrases like "databricks webhook", "databricks notifications", "databricks alerts", "job failure notification", "databricks slack".

Fastify Plugin Creator - Auto-activating skill for Backend Development. Triggers on: fastify plugin creator, fastify plugin creator Part of the Backend Development skill category.

Optimize Finta plan selection and feature usage. Trigger with phrases like "finta cost", "finta pricing", "finta plan selection".

Set up local development workflow for Gamma API integration. Use when building automation scripts, testing API calls locally, or configuring a dev environment with mock responses. Trigger: "gamma local dev", "gamma development setup", "gamma test locally", "gamma mock API", "gamma dev workflow".

Gatling Scenario Creator - Auto-activating skill for Performance Testing. Triggers on: gatling scenario creator, gatling scenario creator Part of the Performance Testing skill category.

Execute Groq primary workflow: chat completions with tool use and JSON mode. Use when implementing chat interfaces, function calling, structured output, or building AI features with Groq's fast inference. Trigger with phrases like "groq chat completion", "groq tool use", "groq function calling", "groq JSON mode".

Execute Groq incident response: triage, mitigation, fallback, and postmortem. Use when responding to Groq-related outages, investigating errors, or running post-incident reviews for Groq integration failures. Trigger with phrases like "groq incident", "groq outage", "groq down", "groq on-call", "groq emergency", "groq broken".

HIPAA Audit Helper - Auto-activating skill for Security Advanced. Triggers on: hipaa audit helper, hipaa audit helper Part of the Security Advanced skill category.

Collect Ideogram debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Ideogram problems. Trigger with phrases like "ideogram debug", "ideogram support bundle", "collect ideogram logs", "ideogram diagnostic".

Create a minimal working Ideogram image generation example. Use when starting a new Ideogram integration, testing your setup, or learning basic Ideogram API patterns. Trigger with phrases like "ideogram hello world", "ideogram example", "ideogram quick start", "simple ideogram code", "first ideogram image".

Set up monitoring, metrics, and alerts for Ideogram integrations. Use when implementing observability for Ideogram operations, tracking costs, or configuring alerting for generation health. Trigger with phrases like "ideogram monitoring", "ideogram metrics", "ideogram observability", "monitor ideogram", "ideogram alerts", "ideogram dashboard".

Collect Juicebox debug evidence for support. Use when creating support tickets, gathering diagnostic info, or preparing error reports for Juicebox support team. Trigger with phrases like "juicebox debug info", "juicebox support bundle", "collect juicebox diagnostics", "juicebox troubleshooting".

Execute Juicebox production deployment checklist. Use when preparing for production launch, validating deployment readiness, or performing pre-launch reviews. Trigger with phrases like "juicebox production", "deploy juicebox prod", "juicebox launch checklist", "juicebox go-live".

K6 Script Generator - Auto-activating skill for Performance Testing. Triggers on: k6 script generator, k6 script generator Part of the Performance Testing skill category.

Upgrade Langfuse SDK versions and migrate between API changes. Use when upgrading Langfuse SDK, handling breaking changes, or migrating between Langfuse versions. Trigger with phrases like "upgrade langfuse", "langfuse migration", "update langfuse SDK", "langfuse breaking changes", "langfuse version".

This skill enables Claude to test load balancing strategies. It validates traffic distribution across backend servers, tests failover scenarios when servers become unavailable, verifies sticky sessions, and assesses health check functionality. Use this skill when the user asks to "test load balancer", "validate traffic distribution", "test failover", "verify sticky sessions", or "test health checks". It is specifically designed for testing load balancing configurations using the `load-balancer-tester` plugin.

Configure multiple MaintainX environments (dev, staging, production). Use when setting up environment-specific configurations, managing multiple MaintainX accounts, or implementing environment promotion. Trigger with phrases like "maintainx environments", "maintainx staging", "maintainx dev prod", "maintainx multi-environment", "maintainx config".

Model Evaluation Metrics - Auto-activating skill for ML Training. Triggers on: model evaluation metrics, model evaluation metrics Part of the ML Training skill category.